出力に重複する値が多いため、以下に示すようにreduce関数を実装しましたが、それでもこのreduceは恒等関数として機能します。つまり、reduceがあってもなくても出力に違いはありません。reduce 関数の何が問題になっていますか?
public class search
{
public static String str="And";
public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, Text>
{
String mname="";
public void configure(JobConf job)
{
mname=job.get(str);
job.set(mname,str);
}
private Text word = new Text();
public Text Uinput =new Text("");
public void map(LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter) throws IOException
{
String mapstr=mname;
Uinput.set(mapstr);
String line = value.toString();
Text fdata = new Text();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens())
{
word.set(tokenizer.nextToken());
fdata.set(line);
if(word.equals(Uinput))
output.collect(fdata,new Text(""));
}
}
}
public static class SReducer extends MapReduceBase implements Reducer<Text, Text, Text, Text>
{
public void reduce(Text key, Iterator<Text> values, OutputCollector<Text, Text> output, Reporter reporter) throws IOException
{
boolean start = true;
//System.out.println("inside reduce :"+input);
StringBuilder sb = new StringBuilder();
while (values.hasNext())
{
if(!start)
start=false;
sb.append(values.next().toString());
}
//output.collect(key, new IntWritable(sum));
output.collect(key, new Text(sb.toString()));
}
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(search.class);
conf.setJobName("QueryIndex");
//JobConf conf = new JobConf(getConf(), WordCount.class);
conf.set(str,args[0]);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(Map.class);
//conf.setCombinerClass(SReducer.class);
conf.setReducerClass(SReducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path("IIndexOut"));
FileOutputFormat.setOutputPath(conf, new Path("searchOut"));
JobClient.runJob(conf);
}
}